TY  - JOUR
A1  - Kimmel, Jacob C.
A1  - Kelley, David R
T1  - Semi-supervised adversarial neural networks for single-cell classification
Y1  - 2021/02/24 
JF  - Genome Research 
JO  - Genome Research 
DO  - 10.1101/gr.268581.120 
SP  - gr.268581.120 
UR  - http://genome.cshlp.org/content/early/2021/02/24/gr.268581.120.abstract 
N2  - Annotating cell identities is a common bottleneck in the analysis of single-cell genomics experiments. Here, we present scNym, a semi-supervised, adversarial neural network that learns to transfer cell identity annotations from one experiment to another. scNym takes advantage of information in both labeled datasets and new, unlabeled datasets to learn rich representations of cell identity that enable effective annotation transfer. We show that scNym effectively transfers annotations across experiments despite biological and technical differences, achieving performance superior to existing methods. We also show that scNym models can synthesize information from multiple training and target datasets to improve performance. In addition to high performance, we show that scNym models are well-calibrated and interpretable with saliency methods. 
ER  -